OBJECTIVE: To describe and evaluate the performance of an automated CAD system for detection of glaucoma from color fundus photographs. DESIGN AND SETTING: Color fundus photographs of 2252 eyes from 1126 subjects were collected from 2 centers: Aravind Eye Hospital, Madurai and Coimbatore, India. The images of 1926 eyes (963 subjects) were used to train an automated image analysis-based system, which was developed to provide a decision on a given fundus image. A total of 163 subjects were clinically examined by 2 ophthalmologists independently and their diagnostic decisions were recorded. The consensus decision was defined to be the clinical reference (gold standard). Fundus images of eyes with disagreement in diagnosis were excluded from the study. The fundus images of the remaining 314 eyes (157 subjects) were presented to 4 graders and their diagnostic decisions on the same were collected. The performance of the system was evaluated on the 314 images, using the reference standard. The sensitivity and specificity of the system and 4 independent graders were determined against the clinical reference standard. RESULTS: The system achieved an area under receiver operating characteristic curve of 0.792 with a sensitivity of 0.716 and specificity of 0.717 at a selected threshold for the detection of glaucoma. The agreement with the clinical reference standard as determined by Cohen κ is 0.45 for the proposed system. This is comparable to that of the image-based decisions of 4 ophthalmologists. CONCLUSIONS AND RELEVANCE: An automated system was presented for glaucoma detection from color fundus photographs. The overall evaluation results indicated that the presented system was comparable in performance to glaucoma classification by a manual grader solely based on fundus image examination.
OBJECTIVE: To describe and evaluate the performance of an automated CAD system for detection of glaucoma from color fundus photographs. DESIGN AND SETTING: Color fundus photographs of 2252 eyes from 1126 subjects were collected from 2 centers: Aravind Eye Hospital, Madurai and Coimbatore, India. The images of 1926 eyes (963 subjects) were used to train an automated image analysis-based system, which was developed to provide a decision on a given fundus image. A total of 163 subjects were clinically examined by 2 ophthalmologists independently and their diagnostic decisions were recorded. The consensus decision was defined to be the clinical reference (gold standard). Fundus images of eyes with disagreement in diagnosis were excluded from the study. The fundus images of the remaining 314 eyes (157 subjects) were presented to 4 graders and their diagnostic decisions on the same were collected. The performance of the system was evaluated on the 314 images, using the reference standard. The sensitivity and specificity of the system and 4 independent graders were determined against the clinical reference standard. RESULTS: The system achieved an area under receiver operating characteristic curve of 0.792 with a sensitivity of 0.716 and specificity of 0.717 at a selected threshold for the detection of glaucoma. The agreement with the clinical reference standard as determined by Cohen κ is 0.45 for the proposed system. This is comparable to that of the image-based decisions of 4 ophthalmologists. CONCLUSIONS AND RELEVANCE: An automated system was presented for glaucoma detection from color fundus photographs. The overall evaluation results indicated that the presented system was comparable in performance to glaucoma classification by a manual grader solely based on fundus image examination.
Authors: Mark Christopher; Akram Belghith; Christopher Bowd; James A Proudfoot; Michael H Goldbaum; Robert N Weinreb; Christopher A Girkin; Jeffrey M Liebmann; Linda M Zangwill Journal: Sci Rep Date: 2018-11-12 Impact factor: 4.379
Authors: Xiaoqin Huang; Jian Sun; Krati Gupta; Giovanni Montesano; David P Crabb; David F Garway-Heath; Paolo Brusini; Paolo Lanzetta; Francesco Oddone; Andrew Turpin; Allison M McKendrick; Chris A Johnson; Siamak Yousefi Journal: Front Med (Lausanne) Date: 2022-09-29